样本：

使用的算法：

代码:

import numpy as np
import pandas as pd
import datetime

from sklearn.impute import SimpleImputer #预处理模块
from sklearn.model_selection import train_test_split #训练集和测试集模块
from sklearn.metrics import classification_report #预测结果评估模块

from sklearn.neighbors import KNeighborsClassifier #K近邻分类器
from sklearn.tree import DecisionTreeClassifier #决策树分类器
from sklearn.naive_bayes import GaussianNB #高斯朴素贝叶斯函数

starttime = datetime.datetime.now()

def load_datasets(feature_paths, label_paths):
feature = np.ndarray(shape=(0, 41)) #列数量和特征维度为41
label = np.ndarray(shape=(0, 1))
for file in feature_paths:
#逗号分隔符读取特征数据，将问号替换标记为缺失值，文件不包含表头
df = pd.read_table(file, delimiter=',', na_values='?', header=None)
#df = df.fillna(df.mean()) #若SimpleImputer无法处理nan，则用pandas本身处理
#使用平均值补全缺失值，然后将数据进行补全
imp = SimpleImputer(missing_values=np.nan, strategy='mean') #此处与教程不同，版本更新，需要使用最新的函数填充NAn，暂不明如何调用
imp.fit(df) #训练预处理器 此句有问题
df = imp.transform(df) #生产预处理结果
feature = np.concatenate((feature, df))#将新读入的数据合并到特征集中

for file in label\_paths:  
    df = pd.read\_table(file, header=None)  
    #将新读入的数据合并到标签集合中  
    label = np.concatenate((label, df))  
#将标签归整为一维向量  
label = np.ravel(label)  
return feature, label

if __name__ == '__main__':
#读取文件，根据本地目录文件夹而设定
path = 'D:\python_source\Machine_study\mooc_data\classification\dataset/'
featurePaths, labelPaths = [], []
for i in range(0, 5, 1): #chr(ord('A') + i)==B/C/D
featurePath = path + chr(ord('A') + i) + '/' + chr(ord('A') + i) + '.feature'
featurePaths.append(featurePath)
labelPath = path + chr(ord('A') + i) + '/' + chr(ord('A') + i) + '.label'
labelPaths.append(labelPath)
#将前4个数据作为训练集读入
x_train, y_train = load_datasets(featurePaths[:4], labelPaths[:4])
#将最后一个数据作为测试集读入
x_test, y_test = load_datasets(featurePaths[4:], labelPaths[4:])
#使用全量数据作为训练集，借助函数将训练数据打乱，便于后续分类器的初始化和训练
x_train, x_, y_train, y_ = train_test_split(x_train, y_train, test_size=0.0)

print('Start training knn')  
knn = KNeighborsClassifier().fit(x\_train, y\_train)    #使用KNN算法进行训练  
print('Training done')  
answer\_knn = knn.predict(x\_test)

print('Start training DT')  
dt = DecisionTreeClassifier().fit(x\_train, y\_train)   #使用决策树算法进行训练  
print('Training done')  
answer\_dt = dt.predict(x\_test)  
print('Prediction done')

print('Start training Bayes')  
gnb = GaussianNB().fit(x\_train, y\_train)    #使用贝叶斯算法进行训练  
print('Training done')  
answer\_gnb = gnb.predict(x\_test)  
print('Prediction done')

#对分类结果从 精确率precision 召回率recall f1值fl-score和支持度support四个维度进行衡量  
print('\\n\\nThe classification report for knn:')  
print(classification\_report(y\_test, answer\_knn))  
print('\\n\\nThe classification report for DT:')  
print(classification\_report(y\_test, answer\_dt))  
print('\\n\\nThe classification report for Bayes:')  
print(classification\_report(y\_test, answer\_gnb))  
endtime = datetime.datetime.now()  
print(endtime - starttime) #时间统计

效果图：